Files
LLeMbas/src/lembas/main.py
T
Jaroslav Beneš bdce2764b1 File attachments: images for vision, PDFs and text into the prompt
Drag, paste or pick a file in the composer. Images go to vision models
as multimodal content parts; PDFs and text files have their content
extracted and placed in the prompt. Verified end to end against
gemma4-e4b-q8 on llama-swap: given a drawing and a text file, it named
the red square and blue circle and read the number out of the document.

Type is decided by inspecting the bytes, never the filename or the
browser's Content-Type -- a .png full of text is stored as text. Images
are downscaled to 1400px and re-encoded: a phone photo is several
megabytes of base64, which is slow and a large slice of the context
window. PDF text is extracted once, at upload, and stored; re-extracting
per request would let a reply change because a parser was upgraded.

Design points worth keeping:

- Images are only sent to models an administrator has marked `vision`.
  This is not graceful degradation -- most endpoints reject the entire
  request rather than ignoring an image part. A plain text turn stays a
  plain string for the same reason: the list form 400s on endpoints that
  do not implement it.
- Images reach the model as base64 data URIs, not links. A local
  endpoint has no route back to LLeMbas, and a hosted one has no
  credentials for it.
- Non-images are served Content-Disposition: attachment with nosniff, so
  an uploaded .html can never execute in this origin. Stored names are
  random; the uploader's name is a label and never a path.
- Uploads are unbound until the message is sent, which is what lets a
  file be removed beforehand. claim() only takes unclaimed rows owned by
  the sender, so a forged id cannot pull in someone else's file.
  Abandoned uploads are swept at startup.
- A scanned PDF says so rather than silently contributing nothing, and
  truncation is declared to the model in the document tag so it can
  admit it did not see page 400.
- "Here, look at this" with no words is a legitimate turn, so a message
  is only empty when it carries neither text nor files.

Also fixes auto-titling, which read message["content"] as a string and
would have broken on the first multimodal turn.

186 tests, ruff clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-21 12:19:59 +02:00

153 lines
5.2 KiB
Python

"""Application factory, lifespan and error handling."""
from __future__ import annotations
import logging
from collections.abc import AsyncIterator
from contextlib import asynccontextmanager
from fastapi import FastAPI, Request, status
from fastapi.responses import JSONResponse, Response
from fastapi.staticfiles import StaticFiles
from starlette.exceptions import HTTPException as StarletteHTTPException
from lembas import __version__
from lembas.api import (
admin,
admin_models,
admin_users,
auth,
chats,
files,
folders,
pages,
preferences,
)
from lembas.api.deps import RedirectToLogin, is_htmx, login_redirect
from lembas.config import settings
from lembas.db.session import init_db
from lembas.web.templating import STATIC_DIR, render
log = logging.getLogger("lembas")
def configure_logging() -> None:
logging.basicConfig(
level=settings.log_level.upper(),
format="%(asctime)s %(levelname)-7s %(name)s: %(message)s",
datefmt="%H:%M:%S",
)
@asynccontextmanager
async def lifespan(app: FastAPI) -> AsyncIterator[None]:
configure_logging()
settings.ensure_dirs()
init_db()
if settings.secret_key_is_ephemeral:
log.warning(
"No LEMBAS_SECRET_KEY set, so a temporary one was generated. Every "
"restart will sign all users out and make stored API keys "
"unreadable. Generate a permanent key with:\n"
' python -c "import secrets; print(secrets.token_urlsafe(48))"'
)
# Files chosen in a composer that was never sent would otherwise sit on
# disk forever. Cheap, and startup is the natural moment for it.
try:
from lembas.db.session import session_scope
from lembas.services.files import sweep_orphans
with session_scope() as db:
sweep_orphans(db)
except Exception: # noqa: BLE001 - housekeeping must never block startup
log.exception("orphaned upload sweep failed")
log.info("LLeMbas %s starting on http://%s:%s", __version__, settings.host, settings.port)
log.info("data directory: %s", settings.data_dir.resolve())
yield
log.info("LLeMbas stopped")
def create_app() -> FastAPI:
app = FastAPI(
title="LLeMbas",
version=__version__,
lifespan=lifespan,
# The API is an implementation detail of the UI, not a product surface.
docs_url="/api/docs" if settings.log_level == "debug" else None,
redoc_url=None,
)
app.mount("/static", StaticFiles(directory=str(STATIC_DIR)), name="static")
app.include_router(pages.router)
app.include_router(auth.router)
app.include_router(preferences.router)
app.include_router(chats.router)
app.include_router(files.router)
app.include_router(folders.router)
app.include_router(admin.router)
app.include_router(admin_users.router)
app.include_router(admin_models.router)
register_error_handlers(app)
return app
def register_error_handlers(app: FastAPI) -> None:
@app.exception_handler(RedirectToLogin)
async def _not_signed_in(request: Request, exc: RedirectToLogin) -> Response:
# An htmx request must not swap a login page into a fragment of the
# chat UI, so tell the browser to navigate instead.
if is_htmx(request):
response = Response(status_code=status.HTTP_204_NO_CONTENT)
response.headers["HX-Redirect"] = "/auth/login"
return response
return login_redirect(exc.next_url)
@app.exception_handler(StarletteHTTPException)
async def _http_error(request: Request, exc: StarletteHTTPException) -> Response:
# JSON callers and htmx fragments want the bare status; humans loading a
# page want a themed page they can navigate away from.
wants_page = "text/html" in request.headers.get("accept", "") and not is_htmx(request)
if not wants_page:
return JSONResponse({"detail": exc.detail}, status_code=exc.status_code)
return render(
request,
"error.html",
{
"status_code": exc.status_code,
"detail": exc.detail,
"flavour": ERROR_FLAVOUR.get(exc.status_code, ERROR_FLAVOUR[500]),
},
status_code=exc.status_code,
)
@app.exception_handler(Exception)
async def _unhandled(request: Request, exc: Exception) -> Response:
log.exception("unhandled error at %s", request.url.path)
if is_htmx(request) or "text/html" not in request.headers.get("accept", ""):
return JSONResponse({"detail": "Internal server error"}, status_code=500)
return render(
request,
"error.html",
{"status_code": 500, "detail": "Something went wrong.",
"flavour": ERROR_FLAVOUR[500]},
status_code=500,
)
# Flavour lives in error pages, empty states and theme names -- never in the
# functional UI. See CLAUDE.md.
ERROR_FLAVOUR = {
403: "Speak, friend, and enter. This door is not yours to open.",
404: "Not all those who wander are lost. This page, however, is.",
500: "The Road goes ever on, but this stretch of it has washed out.",
}
app = create_app()